Information Processing Apparatus, Information Processing Method, and Non-Transitory Computer-Readable Medium

This application is based upon and claims the benefit of priority from Japanese patent application No. 2025-032566, filed on Mar. 3, 2025, the disclosure of which is incorporated herein in its entirety by reference.

The present disclosure relates to an information processing apparatus, an information processing method, and a program.

Techniques for searching for similar cases are known (for example, JP 2008-217362 A).

However, in the technique described in JP 2008-217362 A, for example, there is room for improvement in supporting doctors and the like based on similar cases.

In view of the above-described problems, an example object of the present disclosure is to provide a technique capable of more appropriately supporting doctors and the like based on similar cases.

According to a first example aspect of the present disclosure, there is provided an information processing apparatus including an acquisition unit that acquires clinical information of a plurality of patients, and a control unit that extracts clinical information of another patient whose similarity to the clinical information of a specific patient is equal to or greater than a threshold, and outputs information generated from the clinical information of the other patient based on a sentence instructed by a user.

According to a second example aspect of the present disclosure, there is provided an information processing method including acquiring clinical information of a plurality of patients, extracting clinical information of another patient whose similarity to the clinical information of the specific patient is equal to or greater than a threshold, and outputting information generated from the clinical information of the other patient based on a sentence instructed by the user.

According to a third example aspect of the present disclosure, there is provided a program including acquiring clinical information of a plurality of patients, extracting clinical information of another patient whose similarity to the clinical information of the specific patient is equal to or greater than a threshold, and outputting information generated from the clinical information of the other patient based on a sentence instructed by the user.

According to one aspect, it is possible to more appropriately support doctors and the like based on similar cases.

The principles of the present disclosure will be described with reference to several exemplary example embodiments. It is to be understood that the example embodiments have been described for purposes of exemplification only and will aid those of ordinary skill in the art in understanding and carrying out the present disclosure, without suggesting any limitations on the scope of the present disclosure. The disclosure described in the present description is implemented in various methods other than those described below.

In the following description and claims, unless defined otherwise, all technical and scientific terms used in the present specification have the same meaning as commonly understood by those skilled in the art of the technical field to which the present disclosure belongs.

Hereinafter, example embodiments of the present disclosure will be described with reference to the drawings. Each of the drawings is merely an example to illustrate one or more example embodiments. Each of the drawings is not associated with only one specific example embodiment, but may be associated with one or more other example embodiments. As those of ordinary skill in the art will appreciate, various features or steps described with reference to any one of the drawings may be combined with features or steps illustrated in one or more other drawings, for example, to create an example embodiment that is not explicitly illustrated nor described. All of the features or steps illustrated in any one of the drawings for describing illustrative example embodiments are not necessarily mandatory, and some features or steps may be omitted. The order of the steps described in any of the drawings may be changed as appropriate.

10 10 10 11 12 10 10 1 FIG. 1 FIG. A configuration of an information processing apparatusaccording to an example embodiment will be described with reference to.is a diagram illustrating an example of the configuration of the information processing apparatusaccording to the example embodiment. The information processing apparatusincludes an acquisition unitand a control unit. These units may be achieved by cooperation of one or more programs installed in the information processing apparatusand hardware such as a processor and a memory of the information processing apparatus.

11 12 The acquisition unitacquires clinical information of a plurality of patients. The control unitextracts clinical information of another patient whose similarity to the clinical information of the specific patient is equal to or greater than a threshold, and outputs information generated from the clinical information of the other patient based on a sentence instructed by the user. This makes it possible to more appropriately support doctors and the like based on similar cases.

2 FIG. 2 FIG. 10 10 100 101 102 103 102 104 103 is a diagram illustrating a hardware configuration example of the information processing apparatusaccording to the example embodiment. In the example in, the information processing apparatus(computer) includes a processor, a memory, and a communication interface. These units may be connected by a bus or the like. The memorystores at least a part of a program. The communication interfaceincludes an interface necessary for communication with other network elements.

104 101 102 100 102 102 102 102 100 100 101 101 100 In a case where the programis executed by the cooperation of the processor, the memory, and the like, at least a part of processing according to the example embodiment of the present disclosure is performed by the computer. The memorymay be of any type. The memorymay be a non-transitory computer-readable storage medium, as a non-limiting example. The memorymay also be implemented using any appropriate data storage technique such as a semiconductor-based memory device, magnetic memory device and system, optical memory device and system, a fixed memory, and a removable memory. Although only one memoryis illustrated in the computer, there may be several physically different memory modules in the computer. The processormay be of any type. The processormay include one or more of a general-purpose computer, a dedicated computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture as a non-limiting example. The computermay have a plurality of processors such as an application specific integrated circuit chip that is temporally dependent on a clock that synchronizes a main processor.

Example embodiments of the present disclosure may be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, a microprocessor, or other computing devices.

The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in a program module, and is executed on a related device on a real or virtual processor to execute the processes or methods of the present disclosure. The program module includes routines, programs, libraries, objects, classes, components, data structures, and the like that, for example, execute specific tasks or implement specific abstract data types. Functions of the program module may be combined or divided between program modules as desired in various example embodiments. A machine-executable instruction of the program module can be executed in a local or distributed device. In the distributed device, the program modules can be located on both local and remote storage media.

Program codes for executing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes are provided to a processor or controller of a general-purpose computer, a dedicated computer, or other programmable data processing devices. In a case where the program codes are executed by the processor or controller, the functions/operations in the flowcharts and/or the implemented block diagrams are executed. The program code is executed entirely on a machine, partly on the machine as a stand-alone software package, partly on the machine and partly on a remote machine, or entirely on the remote machine or a server.

The program includes instructions (or software codes) for causing the computer to perform one or more functions described in the example embodiment in a case of being read by the computer. The programs may be stored in a non-transitory computer-readable medium or a tangible storage medium. As an example and not by way of limitation, the computer-readable medium or the tangible storage medium includes a random-access memory (RAM), a read-only memory (ROM), a flash memory, a solid-state drive (SSD) or any other memory technology, a CD-ROM, a digital versatile disc (DVD), a Blu-ray (registered trademark) disc or any other optical disc storage, and a magnetic cassette, a magnetic tape, a magnetic disk storage, or any other magnetic storage device. The program may be transmitted through a transitory computer-readable medium or a communication medium. As an example and not by way of limitation, the transitory computer-readable medium or the communication medium includes propagated signals in electrical, optical, acoustic, or any other form.

10 10 401 3 6 FIG.to 3 FIG. 4 FIG. 5 FIG. 5 6 FIGS.and 3 FIG. Next, an example of a process of the information processing apparatusaccording to the example embodiment will be described with reference to.is a flowchart illustrating an example of the process of the information processing apparatusaccording to the example embodiment.is a diagram illustrating an example of information stored in a clinical information database (DB)according to the example embodiment.is a diagram illustrating an example of a feature item setting screen according to the example embodiment.are diagrams illustrating an example of a display screen according to the example embodiment. The process ofmay be executed in response to an operation by a user (for example, a doctor or the like), for example.

101 11 401 401 401 10 10 In step S, the acquisition unitacquires clinical information of a plurality of patients from the clinical information DB. The data recorded in the clinical information DBmay be generated based on, for example, information acquired from a data warehouse of medical information. The clinical information DBmay be recorded in a storage device inside the information processing apparatusor may be recorded in a storage device outside the information processing apparatus.

4 FIG. 401 In the example of, basic information, medical history, blood test information, medical examination information, surgery information, and information indicating the hospitalization progress are recorded in the clinical information DBin association with the patient ID.

The patient ID is identification information of a patient. The basic information may include, for example, information of items such as gender, age, height, weight, and activities of daily living (ADL). The medical history may include, for example, information of a medical history of items such as heart disease, brain disease, allergy, and steroid medication.

The blood test information may include, for example, information on items such as the number of white blood cells, hemoglobin, albumin, glucose, blood sugar, and total cholesterol. The medical examination information may include, for example, information on items such as a main disease name, TNM (T: tumor, N: lymph nodes, M: metastasis) classification that is an index for evaluating the degree of progression of cancer, lung function, electrocardiogram findings, and chest X-ray findings. The surgery information may include, for example, information of items such as a surgical procedure, a surgery time, a blood loss amount, a blood transfusion amount, and a surgeon's name. The hospitalization progress may include, for example, information on items such as a hospital stay period, complications, and discharge/transfer.

12 102 12 Subsequently, the control unitcalculates similarity between the clinical information of the specific patient and the clinical information of each of the other patients (step S). The specific patient may be, for example, a special person designated by the user. The control unitmay vectorize values of one or more items included in the clinical information of each patient and calculate similarity between the clinical information of the specific patient and the clinical information of other patients in a vector space. In this case, the similarity may be, for example, cosine similarity. The similarity may be calculated (inferred) using, for example, supervised learning or unsupervised learning.

12 501 5 FIG. The control unitmay calculate the similarity between the clinical information of the specific patient and the clinical information of each of the other patients based on one or more items (feature items) instructed by the user among the items included in the clinical information. As a result, for example, the user can designate a viewpoint (item) for determining as a similar case. Therefore, even in a case where the value of the specific item of the specific patient is a remarkable (feature) value, or the like, similar cases can be more appropriately detected. In the example of, on a setting screen, items of age, weight, heart disease, and total cholesterol are designated (selected) by the user as feature items used for determining similarity.

12 12 The control unitmay receive a setting of a feature item used for determination of similarity for each of at least one of a clinical department and a disease name. Then, the control unitmay calculate similarity between the clinical information of the specific patient and the clinical information of each of the other patients based on one or more set feature items among the items included in the clinical information. As a result, for example, even in a case where items to be used for similarity determination are different depending on clinical departments or the like, similar cases can be more appropriately detected.

12 103 12 104 Subsequently, the control unitextracts clinical information of another patient (hereinafter, the patient is also appropriately referred to as a “similar patient”) whose similarity to the clinical information of the specific patient is equal to or greater than a threshold (step S). Subsequently, the control unitreceives an input of a sentence (text) instructed by the user (step S).

12 In a case where a sentence is instructed by the user, the control unitmay display information indicating an item other than the item used for similarity determination among a plurality of items included in the clinical information of the similar patient. As a result, for example, it can support the user to analyze the value of an item not used for determination of a similar case among the items of the specific patient.

611 12 612 611 612 6 FIG. In this case, in a case where an input field (text box)of the instruction sentence illustrated inis designated by a mouse operation or the like, the control unitdisplays a display regionin association with the input field. In the display region, a list of items other than the items used for similarity determination is displayed.

12 10 The control unitmay determine and display a candidate of the instruction sentence relevant to the item designated by the user among the plurality of items included in the clinical information of the similar patient. As a result, for example, it is possible to support the input of the instruction sentence by the user. The candidate sentence of the instruction sentence relevant to the item may be set in the information processing apparatusby the operator or the like, or may be generated using artificial intelligence (AI) such as a large language model.

613 612 12 621 611 12 611 6 FIG. In this case, in a case where the itemof the “hospital stay period” is designated by the user by a click operation or the like in the display regionillustrated in, the control unitmay display the sentence of the candidateof the instruction sentence relevant to the item of the “hospital stay period” in the input field. The control unitmay enable the user to appropriately correct the sentence in the input field.

12 12 The control unitmay generate and display a question sentence for the sentence instructed by the user based on the clinical information of the similar patient. As a result, for example, even in a case where the instruction sentence is not appropriate due to the fluctuation of terms or the like, the input of the appropriate instruction sentence can be received again from the user. In this case, the control unitmay cause the AI such as a large language model to learn the clinical information of the similar patient, generate and display to the user a question about fluctuation between the term in the sentence instructed by the user and the term in the medical record included in the clinical information of the similar patient, the classification range of the disease name, and the like.

12 105 12 Subsequently, the control unitoutputs information generated from the clinical information of the similar patient based on the sentence instructed by the user (step S). Here, the control unitmay generate content (sentence, graph, image, etc.) of an answer to the sentence instructed by the user based on the clinical information of the similar patient using the large language model (LLM). As a result, for example, the user can know the statistical data of the similar case with an input sense such as a chat.

12 12 12 In this case, the control unitmay input the clinical information of the similar patient into the large language model and cause the large language model to learn. Then, the control unitmay instruct the large language model to generate an answer to the sentence instructed by the user in an instruction sentence (prompt) based on the clinical information of the similar patient. Then, the control unitmay cause the large language model to generate an answer by inputting a sentence instructed by the user to the large language model.

12 721 711 7 FIG. In this case, the control unitmay generate information based on the statistical information generated from the clinical information of the similar patient as contents of an answer to the sentence instructed by the user using the large language model. The statistical information may be, for example, a graph showing transition, distribution, or the like of the value of the specific item, or may be a representative value (for example, an average value, a mode value, and a median value) of the specific item value. In the example of, a graphof statistical information is displayed in the display region.

12 12 731 721 12 731 721 7 FIG. The control unitmay display information indicating an item used for similarity determination among a plurality of items included in the clinical information of the similar patient in association with the generated information. As a result, for example, the user can appropriately grasp the determination criterion of the similar case that is the original data such as the statistical information. In this case, as illustrated in, the control unitmay display a display regionof the item used to determine the similarity in association with the graphof the statistical information (In other words, the control unitmay cause the display regionof the item used to determine the similarity to be displayed in association with the graphof the statistical information).

10 10 10 10 The information processing apparatusmay be an apparatus included in one housing, but the information processing apparatusof the present disclosure is not limited thereto. Each unit of the information processing apparatusmay be achieved by, for example, cloud computing including one or more computers. Such an information processing apparatusis also included in an example of the “information processing apparatus” according to the present disclosure.

While the present disclosure has been particularly shown and described with reference to example embodiments thereof, the present disclosure is not limited to these example embodiments. It will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present disclosure as defined by the claims. And each example embodiment can be appropriately combined with other example embodiments.

Some or all of the example embodiments described above may also be described as, but are not limited to, the following Supplementary Notes. Some or all of the elements (for example, configurations and functions) described in each Supplementary Note dependent on Supplementary Note 1 can also be dependent on an independent Supplementary Note of another category in a similar dependency relationship. Some or all of the elements described in any supplementary note may be applied to various types of hardware, software, recording means for recording software, systems, and methods.

an acquisition unit that acquires clinical information of a plurality of patients; and a control unit that extracts clinical information of another patient whose similarity to the clinical information of a specific patient is equal to or greater than a threshold, and outputs information generated from the clinical information of the other patient based on a sentence instructed by a user. An information processing apparatus including:

The information processing apparatus according to Supplementary Note 1, in which the control unit outputs statistical information generated from clinical information of the another patient based on a sentence instructed by the user using a large language model.

The information processing apparatus according to Supplementary Note 1 or 2, in which the control unit extracts, based on an item instructed by the user among a plurality of items included in the clinical information of the another patient, clinical information of the another patient whose similarity to the clinical information of the specific patient is equal to or greater than a threshold.

The information processing apparatus according to Supplementary Note 1 or 2, in which the control unit displays information indicating an item used for determination of the similarity among the plurality of items included in the clinical information of the another patient in association with the generated information.

The information processing apparatus according to Supplementary Note 1 or 2, in which the control unit displays information indicating an item other than the item used for determination of the similarity among the plurality of items included in the clinical information of the another patient in a case where the sentence is instructed by the user.

The information processing apparatus according to Supplementary Note 1 or 2, in which the control unit determines and displays a candidate of an instruction sentence relevant to an item designated by the user among the plurality of items included in the clinical information of the another patient.

The information processing apparatus according to Supplementary Note 1 or 2, in which the control unit receives setting of an item used for determination of the similarity for each of at least one of a clinical department and a disease name.

The information processing apparatus according to Supplementary Note 1 or 2, in which the control unit generates and displays a question sentence for the sentence instructed by the user based on the clinical information of the another patient.

acquiring clinical information of a plurality of patients; and extracting clinical information of another patient whose similarity with the clinical information of a specific patient is equal to or greater than a threshold, and outputting information generated from the clinical information of the other patient based on a sentence instructed by a user. An information processing method including:

acquiring clinical information of a plurality of patients; and extracting clinical information of another patient whose similarity with the clinical information of a specific patient is equal to or greater than a threshold, and outputting information generated from the clinical information of the other patient based on a sentence instructed by a user. A program for causing a computer to execute processing of:

While the disclosure has been particularly shown and described with reference to embodiments thereof, the disclosure is not limited to these embodiments. It will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present disclosure as defined by the claims.